Publications
-
DOCCI: Descriptions of Connected and Contrasting Images,
arXiv 2024.
Yasumasa Onoe, Sunayana Rane, Zachary Berger, Yonatan Bitton, Jaemin Cho, Roopal Garg, Alexander Ku, Zarana Parekh, Jordi Pont-Tuset, Garrett Tanzer, Su Wang, and Jason Baldridge
-
ImageInWords: Unlocking Hyper-Detailed Image Descriptions,
arXiv 2024.
Roopal Garg, Andrea Burns, Burcu Karagol Ayan, Yonatan Bitton, Ceslee Montgomery, Yasumasa Onoe, Andrew Bunner, Ranjay Krishna, Jason Baldridge, and Radu Soricut
-
Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings,
arXiv 2024.
Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kajić, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Chris Knutsen, Cyrus Rashtchian, Jordi Pont-Tuset, and Aida Nematzadeh
-
Propagating Knowledge Updates to LMs Through Distillation,
Neurips 2023.
Shankar Padmanabhan, Yasumasa Onoe, Michael J.Q. Zhang, Greg Durrett, and Eunsol Choi
-
Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge,
ACL 2023.
Yasumasa Onoe, Michael J.Q. Zhang, Shankar Padmanabhan, Greg Durrett, and Eunsol Choi
-
Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting,
arXiv.
Su Wang, Chitwan Saharia, Ceslee Montgomery, Jordi Pont-Tuset, Shai Noy, Stefano Pellegrini, Yasumasa Onoe, Sarah Laszlo, David J. Fleet, Radu Soricut, Jason Baldridge, Mohammad Norouzi, Peter Anderson, William Chan
-
Entity Cloze By Date: What LMs Know About Unseen Entities,
NAACL 2022 Findings.
Yasumasa Onoe, Michael J.Q. Zhang, Eunsol Choi, and Greg Durrett
-
Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection,
MUWS Workshop at WWW 2022.
Diego Garcia-Olano, Yasumasa Onoe, and Joydeep Ghosh
-
Cross-Lingual Fine-Grained Entity Typing,
arXiv 2021.
Nila Selvaraj, Yasumasa Onoe, and Greg Durrett
-
CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge,
NeurIPS 2021 Datasets and Benchmarks Track.
Yasumasa Onoe, Michael J.Q. Zhang, Eunsol Choi, and Greg Durrett
[code]
-
Modeling Fine-Grained Entity Types with Box Embeddings,
ACL 2021.
Yasumasa Onoe, Michael Boratko, Andrew McCallum, and Greg Durrett
[code]
-
Biomedical Interpretable Entity Representations,
ACL 2021 Findings.
Diego Garcia-Olano, Yasumasa Onoe, Ioana Baldini, Joydeep Ghosh, Byron Wallace and Kush Varzney
[code]
-
Interpretable Entity Representations through Large-Scale Typing,
EMNLP 2020 Findings.
Yasumasa Onoe and Greg Durrett
[code]
-
Fine-Grained Entity Typing for Domain Independent Entity Linking,
AAAI 2020.
Yasumasa Onoe and Greg Durrett
[code]
[poster]
-
Learning to Denoise Distantly-Labeled Data for Entity Typing,
NAACL 2019.
Yasumasa Onoe and Greg Durrett
[code]
[poster]
-
Gated Word-Character Recurrent Language Model,
EMNLP 2016.
Yasumasa Miyamoto (Onoe) and Kyunghyun Cho
[code]